INDEX

Explanations

phrases indicating a change in location or situation

oai_token-act-pair · gpt-3.5-turbo

phrases related to ongoing actions or experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pg

-0.74

 Magicka

-0.73

 bandwagon

-0.64

 Edition

-0.63

 lineback

-0.62

inho

-0.61

roller

-0.59

 thirst

-0.59

aug

-0.57

 vibe

-0.57

POSITIVE LOGITS

redients

0.71

ãĤ¢ãĥ«

0.69

ãĥ¼ãĥĨ

0.67

ients

0.64

ãĥ¼ãĥĨãĤ£

0.64

 Heard

0.64

ushima

0.64

iated

0.63

 Pengu

0.63

itially

0.61

Activations Density 0.166%

phrases indicating a change in location or situation

phrases related to ongoing actions or experiences

No Comments

No Known Activations